Abstract: A computer-implementable method for managing a cognitive graph comprising: receiving data from a plurality of data sources; processing the data from the plurality of data sources, the processing the data from the plurality of data sources identifying a plurality of knowledge elements; and, storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data.

Abstract: A model learning unit of an anomaly detection device learns a relational expression between vibration strengths at frequencies based on a time series of frequency characteristics of a vibration strength detected during a learning period by a vibration sensor placed on a monitoring target. The anomaly detection unit learns a relational expression between vibration strengths at frequencies based on a time series of frequency characteristics of a vibration strength detected during a new period by the vibration sensor. Then, the anomaly detection unit determines whether or not there is an anomaly in the monitoring target based on a relational expression related to a new frequency, which is different from the relational expression learned during the learning period.

Abstract: A computer-implementable method for managing a cognitive graph comprising: receiving data from a data source; determining whether the data comprises text; processing the data, the processing comprising performing a parsing operation on the data, the processing the data identifying a plurality of knowledge elements based upon the parsing operation; and, storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data.

Abstract: A system comprising: a processor; a data bus coupled to the processor; and a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus. The computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for: receiving data from a data source; determining whether the data comprises text; processing the data, the processing comprising performing a lossless parsing operation on the data, the processing the data identifying a plurality of knowledge elements based upon the parsing operation; and, storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data.

Abstract: A reconfigurable automatic document-classification system and method provides classification metrics to a user and enables the user to reconfigure the classification model. The user can refine the classification model by adding or removing exemplars, creating, editing or deleting rules, or performing other such adjustments to the classification model. This technology enhances the overall transparency and defensibility of the auto-classification process.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: The application provides an operation method and device. Quantized data is looked up to realize an operation, which simplifies the structure and reduces the computation energy consumption of the data, meanwhile, a plurality of operations are realized.

Abstract: A webpage navigation of a user over a timeframe and a second webpage navigation of a second user over a second timeframe may be received. A time-variant variable-order Markov model, comprising a context tree, may be generated utilizing the webpage navigation and the second webpage navigation. A third webpage navigation of a third user may be received. A probability that the third user may interact with content, that the third user is a non-human entity, and/or that the third user will access a website may be determined based upon an evaluation of the third webpage navigation using the time-variant variable-order Markov model. A second client device is instructed to present the content to the third user, to present a human verification mechanism to the third user, and/or to instruct a server, providing the website, to alter a server capacity for the website.

Abstract: A computer trains a classification model. (A) An estimation vector is computed for each observation vector using a weight value, a mean vector, and a covariance matrix. The estimation vector includes a probability value for each class of a plurality of classes for each observation vector that indicates a likelihood that each observation vector is associated with each class. A subset of the plurality of observation vectors has a predefined class assignment. (B) The weight value is updated using the computed estimation vector. (C) The mean vector for each class is updated using the computed estimation vector. (D) The covariance matrix for each class is updated using the computed estimation vector. (E) A convergence parameter value is computed. (F) A classification model is trained by repeating (A) to (E) until the computed convergence parameter value indicates the mean vector for each class of the plurality of classes is converged.

Abstract: A computing system trains a clustering model. A responsibility parameter vector includes a probability value of a cluster membership in each cluster for each respective observation vector. (A) Parameter values for a normal-Wishart distribution are computed for each cluster using a mean value, an inverse precision parameter value, each observation vector, and each respective responsibility parameter vector. (B) The responsibility parameter vector is updated using a multivariate student t-distribution function with the computed parameter values for the normal-Wishart distribution and a respective observation vector of the observation vectors as input values. (C) A convergence parameter value is computed. (D) (A) to (C) are repeated until the computed convergence parameter value indicates the responsibility parameter vector defined for each observation vector is converged. A cluster membership is determined for each observation vector using a respective, updated responsibility parameter vector.

Abstract: [Object] An object is to provide a statistical acoustic model adaptation method capable of efficient adaptation of an acoustic model using DNN with training data under a specific condition and achieving higher accuracy. [Solution] A method of speaker adaptation of an acoustic model using DNN includes the steps of: storing speech data 90 to 98 of different speakers separately in a first storage device; preparing speaker-by-speaker hidden layer modules 112 to 120; performing preliminary learning of all layers 42, 44, 110, 48, 50, 52 and 54 of a DNN 80 by switching and selecting the speech data 90 to 98 while dynamically replacing a specific layer 110 with hidden layer modules 112 to 120 corresponding to the selected speech data; replacing the specific layer 110 of the DNN that has completed the preliminary learning with an initial hidden layer; and training the DNN with speech data of a specific speaker while fixing parameters of layers other than the initial hidden layer.

Abstract: A method comprising calculating output values of a plurality of linear nodes connected to a maxout node in a neural network, calculating a temporary maximum value among the output values during the calculation of the output values, and terminating the calculation of a final output value of a first linear node of the plurality of linear nodes in response to a condition that a difference between the temporary maximum value and a temporary output value of the first linear node exceeds a threshold value during the calculation of the output values.

Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR A DIGITAL CONVERSATION MANAGEMENT PLATFORM (“DCM-Platform”) transforms digital dialogue from consumers, client demands and, Internet search inputs via DCM-Platform components into tradable digital assets, and client needs based artificial intelligence campaign plan outputs. In one implementation, The DCM-Platform may capture and examine conversations between individuals and artificial intelligence conversation agents. These agents may be viewed as assets. One can measure the value and performance of these agents by assessing their performance and ability to generate revenue from prolonging conversations and/or ability to effect sales through conversations with individuals.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR A DIGITAL CONVERSATION MANAGEMENT PLATFORM (“DCM-Platform”) transforms digital dialogue from consumers, client demands and, Internet search inputs via DCM-Platform components into tradable digital assets, and client needs based artificial intelligence campaign plan outputs. In one implementation, The DCM-Platform may capture and examine conversations between individuals and artificial intelligence conversation agents. These agents may be viewed as assets. One can measure the value and performance of these agents by assessing their performance and ability to generate revenue from prolonging conversations and/or ability to effect sales through conversations with individuals.

Abstract: A system and method includes receiving a tuning work request for tuning an external machine learning model; implementing a plurality of distinct queue worker machines that perform various tuning operations based on the tuning work data of the tuning work request; implementing a plurality of distinct tuning sources that generate values for each of the one or more hyperparameters of the tuning work request; selecting, by one or more queue worker machines of the plurality of distinct queue worker machines, one or more tuning sources of the plurality of distinct tuning sources for tuning the one or more hyperparameters; and using the selected one or more tuning sources to generate one or more suggestions for the one or more hyperparameters, the one or more suggestions comprising values for the one or more hyperparameters of the tuning work request.

Abstract: An apparatus comprises a processing platform configured to implement a machine learning system for automated generation of predicted reliability measures and associated early warning indicators for product and part combinations. The machine learning system comprises a data aggregation module configured to extract product and part data from a big data repository, and a reliability predictor configured to generate predicted reliability measures for respective ones of the product and part combinations utilizing a shared model that is determined based at least in part on the extracted product and part data. The machine learning system processes the predicted reliability measures to generate early warning indicators relating to particular ones of the product and part combinations having predicted reliability measures that fail to meet one or more specified criteria.

Abstract: Exemplary methods and devices herein receive an inquiry and automatically analyze words used in the inquiry, potential answers, and data maintained by evidence sources using the computerized device to determine the sensitivity level associated with the inquiry. The sensitivity level associated with the inquiry represents an emotional and cognitive state of the user. Such methods and devices automatically generate at least one follow-up question based on the sensitivity level associated with the inquiry and receive a follow-up response into the computerized device in response to the follow-up question(s). The methods and devices also automatically produce scores for the potential answers using the computerized device based on the inquiry, the follow-up responses, and ratings of the evidence sources. Following this, these methods and devices automatically generate output answers to the inquiry based on the sensitivity level associated with the inquiry using the computerized device.

Abstract: An approach for predictively scoring test case results in real-time. Test case results associated with a test run are received by a software testing environment. Using predictive statistical models, test case results and attribute relationships are matched against model rules and test case history. A statistical correlation and confidence parameter provide the ability to generate test case relationships for predicting the outcome of other test cases in the test run. The test case relationships are transformed into scoring results and output for the further processing.

Abstract: An Internet-based agenda data analysis system may include at least one processor configured to maintain a list of user-selectable agenda issues, present to a user via a user interface, the list of user-selectable agenda issues, and receive via the user interface, based on a selection from the list, agenda issues of interest to an organization. The processor may be configured to access information scraped from the Internet to determine, for a plurality of policymakers, individual policymaker data from which an alignment position of each policymaker on each of the agenda issues is determinable, calculate alignment position data from the individual policymaker data, the alignment position data corresponding to relative positions of each of the plurality of policymakers on each of the plurality of selected issues, and transform the alignment position data into a graphical display that presents the alignment positions of multiple policymakers.